© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2841
    Prev
    Next
    INDEX
    Explanations

    date and time related characters, such as hyphens, colons, forward slashes, plus signs, and the letters T and Z

    oai_token-act-pair · gemini-2.0-flash

    - /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -
    -0.70
    SpringBootTest
    -0.63
    (
    -0.60
    sidemargin
    -0.49
    [
    -0.47
    ,
    -0.47
     ex
    -0.47
     C
    -0.47
     on
    -0.47
    utnik
    -0.47
    POSITIVE LOGITS
     quæ
    0.82
     pleaſure
    0.73
     Anſ
    0.72
     himſelf
    0.71
     itſelf
    0.68
     Theſe
    0.68
    enumi
    0.67
     MainAxisSize
    0.66
     Cæsar
    0.65
    crollView
    0.63
    Activations Density 8.342%

    No Known Activations